{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/fine-tuning-graph-neural-networks-via-graph","title":"Fine-Tuning Graph Neural Networks via Graph Topology induced Optimal Transport","arxiv_id":"2203.10453","date":"2022-03-20","proceeding":null,"authors":["Jiying Zhang","Xi Xiao","Long-Kai Huang","Yu Rong","Yatao Bian"],"abstract":"Recently, the pretrain-finetuning paradigm has attracted tons of attention in graph learning community due to its power of alleviating the lack of labels problem in many real-world applications. Current studies use existing techniques, such as weight constraint, representation constraint, which are derived from images or text data, to transfer the invariant knowledge from the pre-train stage to fine-tuning stage. However, these methods failed to preserve invariances from graph structure and Graph Neural Network (GNN) style models. In this paper, we present a novel optimal transport-based fine-tuning framework called GTOT-Tuning, namely, Graph Topology induced Optimal Transport fine-Tuning, for GNN style backbones. GTOT-Tuning is required to utilize the property of graph data to enhance the preservation of representation produced by fine-tuned networks. Toward this goal, we formulate graph local knowledge transfer as an Optimal Transport (OT) problem with a structural prior and construct the GTOT regularizer to constrain the fine-tuned model behaviors. By using the adjacency relationship amongst nodes, the GTOT regularizer achieves node-level optimal transport procedures and reduces redundant transport procedures, resulting in efficient knowledge transfer from the pre-trained models. We evaluate GTOT-Tuning on eight downstream tasks with various GNN backbones and demonstrate that it achieves state-of-the-art fine-tuning performance for GNNs.","url_abs":"https://arxiv.org/abs/2203.10453v1","url_pdf":"https://arxiv.org/pdf/2203.10453v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"fine-tuning-graph-neural-networks-via-graph","repo_url":"https://github.com/youjibiying/gtot-tuning","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"graph-classification","task_name":"Graph Classification"},{"task_slug":"graph-learning","task_name":"Graph Learning"},{"task_slug":"graph-neural-network","task_name":"Graph Neural Network"},{"task_slug":"molecular-property-prediction","task_name":"Molecular Property Prediction"},{"task_slug":"transfer-learning","task_name":"Transfer Learning"}],"methods":[{"method_slug":"graph-neural-network","method_name":"Graph Neural Network"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/graph-classification-on-bace","task":"Graph Classification","dataset":"BACE","model":"GTOT-Tuning","rank_in_archive_order":2,"of":2,"metrics":{"ROC-AUC":"83.4"},"uses_additional_data":false},{"leaderboard":"/sota/graph-classification-on-bbbp","task":"Graph Classification","dataset":"BBBP","model":"GTOT-Tuning","rank_in_archive_order":2,"of":3,"metrics":{"ROC-AUC":"70"},"uses_additional_data":false},{"leaderboard":"/sota/graph-classification-on-hiv","task":"Graph Classification","dataset":"HIV","model":"GTOT-Tuning","rank_in_archive_order":1,"of":3,"metrics":{"ROC-AUC":"78.2"},"uses_additional_data":false},{"leaderboard":"/sota/graph-classification-on-muv","task":"Graph Classification","dataset":"MUV","model":"GTOT-Tuning","rank_in_archive_order":1,"of":2,"metrics":{"ROC-AUC":"80"},"uses_additional_data":false},{"leaderboard":"/sota/graph-classification-on-sider","task":"Graph Classification","dataset":"SIDER","model":"GTOT-Tuning","rank_in_archive_order":1,"of":2,"metrics":{"ROC-AUC":"63.5"},"uses_additional_data":false},{"leaderboard":"/sota/graph-classification-on-tox21","task":"Graph Classification","dataset":"Tox21","model":"GTOT-Tuning","rank_in_archive_order":3,"of":3,"metrics":{"ROC-AUC":"75.6"},"uses_additional_data":false},{"leaderboard":"/sota/graph-classification-on-toxcast","task":"Graph Classification","dataset":"ToxCast","model":"GTOT-Tuning","rank_in_archive_order":3,"of":3,"metrics":{"ROC-AUC":"64"},"uses_additional_data":false},{"leaderboard":"/sota/graph-classification-on-clintox","task":"Graph Classification","dataset":"clintox","model":"GTOT-Tuning","rank_in_archive_order":2,"of":2,"metrics":{"ROC-AUC":"72"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2203.10453","atlas_url":"https://app.syntology.ai/?focus=2203.10453","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.10453"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/youjibiying/gtot-tuning","reach":null}],"summary":{"unverified":2},"by_repo_kind":{"official":{"samples":2,"ran":0,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"4a82591e4f77c220","entry":"GTOT","repo":"youjibiying/gtot-tuning","repo_kind":"official","path":"chem/ftlib/finetune/gtot_tuning.py","file_url":"https://github.com/youjibiying/gtot-tuning/blob/HEAD/chem/ftlib/finetune/gtot_tuning.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"4a82591e4f77c220"}},{"code_sha256_prefix":"dc6ca28379960dea","entry":"GTOTRegularization","repo":"youjibiying/gtot-tuning","repo_kind":"official","path":"chem/ftlib/finetune/gtot_tuning.py","file_url":"https://github.com/youjibiying/gtot-tuning/blob/HEAD/chem/ftlib/finetune/gtot_tuning.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"dc6ca28379960dea"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}